Level-Set Algorithm Based System for Segmentation of Medical Images

Segmentation means dividing an image into connected regions. It is the basic procedure to enhance the image. This process accommodate to identify and envisage objects in an image. In medical imaging, this algorithm is useful to elevate organ, cells or structures in the body. But there are many difficulties occurred in the segmentation process, they may be noise, variation of contrast, motion blurring artifacts. There are many segmentation methods have been proposed from the past years, but we used in this paper the segmentation algorithm based on level-set. The application in this work is to assess the performance of the six level-set algorithms on a given MRI image of Brain segmentation in 2D. The initialization implemented in this process is common for all the algorithms and the reference contour chosen for the computation of Dice criterion. MATLAB tool based application is used to evaluate the performance of various level-set algorithms in the segmentation of an image particularly on medical images. Classical methods such as Chan & Vese and Shi algorithms only evolve on their narrow band and are region based. We propose the recent methods such as Li and Lankton algorithms which are localized region based. Analyse and compare various level set algorithms on medical images in terms of Dice criterion, computational time , PSNR, Hausdorff distance and the mean sum of squared distance(MSSD).